Improvements to the Monte Carlo version of RGoal algorithm
-
- YUUJI Ichisugi
- AIST
-
- HIDEMOTO Nakada
- AIST
-
- NAOTO Takahashi
- AIST
-
- IZUMI Takeuti
- AIST
-
- TAKASHI Sano
- Toyo University
Bibliographic Information
- Other Title
-
- モンテカルロ版 RGoal アルゴリズムの改良
Abstract
<p>We previously proposed a hierarchical reinforcement learning algorithm, RGoal, that allows recursive subroutine calls. In this paper, we improve the definition of the reference value for relative value in the Monte Carlo version of RGoal in order to stabilize learning when subroutines are shared between different tasks. The implemented algorithm was confirmed to work in several test tasks.</p>
Journal
-
- JSAI Technical Report, Type 2 SIG
-
JSAI Technical Report, Type 2 SIG 2023 (AGI-026), 50-55, 2024-03-08
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390299395584398720
-
- ISSN
- 24365556
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Allowed